Portrait de Ankur Sikarwar n'est pas disponible

Ankur Sikarwar

ankursikarwardc@gmail.com
Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e
Aishwarya Agrawal
Sujets de recherche
Apprentissage de représentations
Apprentissage profond
Traitement du langage naturel
Vision par ordinateur
Site web
Google Scholar
GitHub

Publications

The Promise of RL for Autoregressive Image Editing
Saba Ahmadi
Rabiul Awal
Ankur Sikarwar
Amirhossein Kazemnejad
Ge Ya Luo
Juan A. Rodriguez
Sai Rajeswar
Siva Reddy
Chris Pal
Benno Krojer
Aishwarya Agrawal
We explore three strategies to enhance performance on a wide range of image editing tasks: supervised fine-tuning (SFT), reinforcement learn… (voir plus)ing (RL), and Chain-of-Thought (CoT) reasoning. In order to study all these components in one consistent framework, we adopt an autoregressive multimodal model that processes textual and visual tokens in a unified manner. We find RL combined with a large multi-modal LLM verifier to be the most effective of these strategies. As a result, we release EARL: Editing with Autoregression and RL, a strong RL-based image editing model that performs competitively on a diverse range of edits compared to strong baselines, despite using much less training data. Thus, EARL pushes the frontier of autoregressive multimodal models on image editing. We release our code, training data, and trained models at https://github.com/mair-lab/EARL.
2025-08-01
ArXiv (prépublication)
arxiv.org
arxiv.org
The Promise of RL for Autoregressive Image Editing
Saba Ahmadi
Rabiul Awal
Ankur Sikarwar
Amirhossein Kazemnejad
Ge Ya Luo
Juan A. Rodriguez
Sai Rajeswar
Siva Reddy
Chris Pal
Benno Krojer
Aishwarya Agrawal
We explore three strategies to enhance performance on a wide range of image editing tasks: supervised fine-tuning (SFT), reinforcement learn… (voir plus)ing (RL), and Chain-of-Thought (CoT) reasoning. In order to study all these components in one consistent framework, we adopt an autoregressive multimodal model that processes textual and visual tokens in a unified manner. We find RL combined with a large multi-modal LLM verifier to be the most effective of these strategies. As a result, we release EARL: Editing with Autoregression and RL, a strong RL-based image editing model that performs competitively on a diverse range of edits compared to strong baselines, despite using much less training data. Thus, EARL pushes the frontier of autoregressive multimodal models on image editing. We release our code, training data, and trained models at https://github.com/mair-lab/EARL.
2025-08-01
arXiv (publié)
doi.org
arxiv.org